Get detailed information about a specific expense, including all users involved and their shares.
AI agents call splitwise_get_expense to retrieve information from Splitwise MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves expense data without modifying, deleting, or executing any actions. It is purely informational, allowing users to view expense details including users involved and their shares. There are no irreversible changes, financial transactions, or external command execution.
From the tool's definition Tool name 'splitwise_get_expense' and description 'Get detailed information about a specific expense' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
Get detailed information about a specific expense, including all users involved and their shares. It is categorised as a Read tool in the Splitwise MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Splitwise MCP Server MCP server in PolicyLayer and add a rule for splitwise_get_expense: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Splitwise MCP Server. Nothing to install.
splitwise_get_expense is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the splitwise_get_expense rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for splitwise_get_expense. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
splitwise_get_expense is provided by the Splitwise MCP Server MCP server (svarun115/splitwise-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →